Automated software testing is a cornerstone of modern software engineering, yet traditional approaches struggle to keep pace with the complexity and rapid evolution of contemporary applications. This paper investigates the integration of generative artificial intelligence (AI) and large language models (LLMs) into automated software testing workflows. We review the state of the art in AI-driven test case generation, test script maintenance, and defect prediction, highlighting how generative models can analyze source code, requirements, and user behavior to produce comprehensive and adaptive test suites. Our study synthesizes recent research and industry case studies, demonstrating that generative AI and LLMs significantly enhance test coverage, reduce manual effort, and accelerate release cycles. However, challenges remain in model interpretability, data quality, and resource requirements. We discuss these limitations and propose future research directions, including explainable AI for testing and domain-specific model adaptation. The findings indicate that the synergy between human expertise and intelligent automation is essential for ensuring software reliability in increasingly complex environments. This work provides a comprehensive overview for researchers and practitioners seeking to leverage generative AI and LLMs in software testing
Subramaniam et al. (Sat,) studied this question.